migration: preserve sentiment and pools slice
This commit is contained in:
leefer
+4
-493
@@ -1,496 +1,7 @@
|
||||
from __future__ import annotations
|
||||
"""Compatibility alias for the canonical sentiment engine implementation."""
|
||||
|
||||
from copy import deepcopy
|
||||
from statistics import mean, median
|
||||
from typing import Any
|
||||
import sys
|
||||
|
||||
from backend.features.sentiment import engine as _implementation
|
||||
|
||||
COMPONENT_WEIGHTS = {
|
||||
"breadth": 20,
|
||||
"limit_ecology": 25,
|
||||
"profit_effect": 30,
|
||||
"ladder_structure": 15,
|
||||
"liquidity": 10,
|
||||
}
|
||||
|
||||
SENTIMENT_ENGINE_VERSION = 2
|
||||
|
||||
|
||||
def _number(value: Any, default: float = 0.0) -> float:
|
||||
try:
|
||||
number = float(value)
|
||||
return number if number == number else default
|
||||
except (TypeError, ValueError):
|
||||
return default
|
||||
|
||||
|
||||
def _clamp(value: float, lower: float = 0.0, upper: float = 100.0) -> float:
|
||||
return min(upper, max(lower, value))
|
||||
|
||||
|
||||
def _linear(value: float, low: float, high: float) -> float:
|
||||
if high <= low:
|
||||
return 50.0
|
||||
return _clamp((value - low) / (high - low) * 100)
|
||||
|
||||
|
||||
def _percentile(value: float, history: list[float]) -> float:
|
||||
if not history:
|
||||
return 50.0
|
||||
below = sum(item < value for item in history)
|
||||
equal = sum(item == value for item in history)
|
||||
return _clamp((below + equal * 0.5) / len(history) * 100)
|
||||
|
||||
|
||||
def _adaptive_score(value: float, fixed: float, history: list[float]) -> float:
|
||||
if len(history) < 20:
|
||||
return fixed
|
||||
return fixed * 0.25 + _percentile(value, history[-250:]) * 0.75
|
||||
|
||||
|
||||
def _trade_date(payload: dict[str, Any]) -> str:
|
||||
meta = payload.get("meta") or {}
|
||||
return str(meta.get("trade_date") or payload.get("_snapshot_date") or "").replace("-", "")
|
||||
|
||||
|
||||
def _deduplicate_snapshots(snapshots: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
by_trade_date: dict[str, dict[str, Any]] = {}
|
||||
for payload in snapshots:
|
||||
trade_date = _trade_date(payload)
|
||||
if trade_date:
|
||||
by_trade_date[trade_date] = payload
|
||||
return [by_trade_date[key] for key in sorted(by_trade_date)]
|
||||
|
||||
|
||||
def _snapshot_stats(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
overview = payload.get("overview") or {}
|
||||
meta = payload.get("meta") or {}
|
||||
limits = list(payload.get("limits") or [])
|
||||
broken = list(payload.get("broken") or [])
|
||||
down_limits = list(payload.get("down_limits") or [])
|
||||
yesterday = list(payload.get("yesterday_limits") or [])
|
||||
|
||||
limit_up = len(limits) if limits else int(_number(overview.get("limit_up_count")))
|
||||
broken_count = len(broken) if broken else int(_number(overview.get("broken_count")))
|
||||
limit_down = len(down_limits) if down_limits else int(_number(overview.get("limit_down_count")))
|
||||
streaks = [max(1, int(_number(row.get("streak"), 1))) for row in limits]
|
||||
first_board = sum(streak == 1 for streak in streaks)
|
||||
second_board = sum(streak == 2 for streak in streaks)
|
||||
three_plus = sum(streak >= 3 for streak in streaks)
|
||||
max_height = max(streaks, default=0)
|
||||
present_levels = set(streaks)
|
||||
ladder_completeness = (
|
||||
sum(level in present_levels for level in range(1, max_height + 1)) / max_height * 100
|
||||
if max_height else 0.0
|
||||
)
|
||||
|
||||
up_count = int(_number(overview.get("up_count")))
|
||||
down_count = int(_number(overview.get("down_count")))
|
||||
flat_count = int(_number(overview.get("flat_count")))
|
||||
active_count = up_count + down_count
|
||||
breadth_ratio = up_count / max(active_count, 1) * 100
|
||||
seal_rate = _number(overview.get("seal_rate"))
|
||||
if not seal_rate and limit_up + broken_count:
|
||||
seal_rate = limit_up / (limit_up + broken_count) * 100
|
||||
|
||||
previous_limit_count = len(yesterday)
|
||||
previous_positive_count = sum(_number(row.get("current_change")) > 0 for row in yesterday)
|
||||
previous_positive_rate = previous_positive_count / max(previous_limit_count, 1) * 100
|
||||
advanced_count = sum(row.get("outcome") == "晋级" for row in yesterday)
|
||||
advance_rate = advanced_count / max(previous_limit_count, 1) * 100
|
||||
average_previous_change = (
|
||||
mean(_number(row.get("current_change")) for row in yesterday) if yesterday else 0.0
|
||||
)
|
||||
median_previous_change = (
|
||||
median(_number(row.get("current_change")) for row in yesterday) if yesterday else 0.0
|
||||
)
|
||||
severe_loss_count = sum(_number(row.get("current_change")) <= -5 for row in yesterday)
|
||||
severe_loss_rate = severe_loss_count / max(previous_limit_count, 1) * 100
|
||||
previous_down_count = sum(row.get("outcome") == "跌停" for row in yesterday)
|
||||
high_previous = [row for row in yesterday if int(_number(row.get("prior_streak"), 1)) >= 2]
|
||||
high_positive_rate = (
|
||||
sum(_number(row.get("current_change")) > 0 for row in high_previous)
|
||||
/ max(len(high_previous), 1)
|
||||
* 100
|
||||
)
|
||||
|
||||
amount_billion = _number(overview.get("amount_billion"))
|
||||
limit_amount_billion = sum(_number(row.get("amount_billion")) for row in limits)
|
||||
return {
|
||||
"trade_date": _trade_date(payload),
|
||||
"previous_trade_date": str(meta.get("previous_trade_date") or "").replace("-", ""),
|
||||
"up_count": up_count,
|
||||
"down_count": down_count,
|
||||
"flat_count": flat_count,
|
||||
"breadth_ratio": round(breadth_ratio, 1),
|
||||
"limit_up_count": limit_up,
|
||||
"first_board_count": first_board,
|
||||
"second_board_count": second_board,
|
||||
"three_plus_count": three_plus,
|
||||
"max_height": max_height,
|
||||
"ladder_completeness": round(ladder_completeness, 1),
|
||||
"broken_count": broken_count,
|
||||
"limit_down_count": limit_down,
|
||||
"seal_rate": round(seal_rate, 1),
|
||||
"previous_limit_count": previous_limit_count,
|
||||
"previous_positive_count": previous_positive_count,
|
||||
"previous_positive_rate": round(previous_positive_rate, 1),
|
||||
"advance_rate": round(advance_rate, 1),
|
||||
"average_previous_change": round(average_previous_change, 2),
|
||||
"median_previous_change": round(median_previous_change, 2),
|
||||
"severe_loss_count": severe_loss_count,
|
||||
"severe_loss_rate": round(severe_loss_rate, 1),
|
||||
"previous_down_count": previous_down_count,
|
||||
"high_positive_rate": round(high_positive_rate, 1),
|
||||
"amount_billion": round(amount_billion, 1),
|
||||
"limit_amount_billion": round(limit_amount_billion, 2),
|
||||
}
|
||||
|
||||
|
||||
def _sentiment_label(score: float) -> str:
|
||||
if score >= 80:
|
||||
return "情绪高涨"
|
||||
if score >= 60:
|
||||
return "情绪偏强"
|
||||
if score >= 40:
|
||||
return "情绪中性"
|
||||
if score >= 20:
|
||||
return "情绪偏弱"
|
||||
return "情绪冰点"
|
||||
|
||||
|
||||
def _phase_signal(score: float, momentum: float, profit_score: float) -> str:
|
||||
if score < 25:
|
||||
return "修复" if momentum > 3 else "冰点"
|
||||
if score < 45:
|
||||
return "修复" if momentum > 3 else "退潮"
|
||||
if score >= 80:
|
||||
return "高潮" if momentum >= -2 and profit_score >= 60 else "分化"
|
||||
if score >= 65:
|
||||
return "分化" if momentum < -3 or profit_score < 50 else "发酵"
|
||||
if momentum < -5:
|
||||
return "退潮"
|
||||
return "发酵" if momentum >= 0 and profit_score >= 45 else "分化"
|
||||
|
||||
|
||||
def _confirmed_phase(
|
||||
previous: dict[str, Any] | None,
|
||||
score: float,
|
||||
day_change: float,
|
||||
systemic_health: float,
|
||||
profit_score: float,
|
||||
ecology_score: float,
|
||||
phase_signal: str,
|
||||
extreme_ice: bool,
|
||||
fermentation_signal_count: int,
|
||||
) -> tuple[str, str]:
|
||||
if previous is None:
|
||||
return phase_signal, "首个连续交易日，采用原始阶段信号"
|
||||
previous_phase = str(previous.get("phase") or phase_signal)
|
||||
if extreme_ice:
|
||||
return "冰点", "市场宽度与跌停数量触发极端冰点"
|
||||
|
||||
recovery = day_change >= 6 and score >= 25 and systemic_health >= 24
|
||||
fermentation_confirmed = fermentation_signal_count >= 2
|
||||
climax_ready = (
|
||||
score >= 80
|
||||
and profit_score >= 60
|
||||
and systemic_health >= 60
|
||||
and ecology_score >= 70
|
||||
)
|
||||
|
||||
if previous_phase == "冰点":
|
||||
return ("修复", "冰点后首次有效回升") if recovery else ("冰点", "冰点尚未形成有效修复")
|
||||
|
||||
if previous_phase == "退潮":
|
||||
if score < 25:
|
||||
return "冰点", "退潮继续下探至冰点区间"
|
||||
return ("修复", "退潮后出现有效回升") if recovery else ("退潮", "退潮尚未形成有效修复")
|
||||
|
||||
if previous_phase == "修复":
|
||||
if score < 25:
|
||||
return "冰点", "修复失败并重新跌入冰点区间"
|
||||
if day_change <= -6 and score < 45:
|
||||
return "退潮", "修复失败且温度显著回落"
|
||||
if fermentation_confirmed:
|
||||
return "发酵", "发酵条件连续两个交易日成立"
|
||||
return "修复", "修复延续，等待发酵确认"
|
||||
|
||||
if previous_phase == "发酵":
|
||||
if score < 25:
|
||||
return "冰点", "发酵阶段出现极端情绪坍塌"
|
||||
if score < 45 and (day_change < 0 or systemic_health < 35):
|
||||
return "退潮", "发酵阶段温度与系统健康度同步转弱"
|
||||
if climax_ready:
|
||||
return "高潮", "温度、赚钱效应与涨停生态共同达到高潮条件"
|
||||
if phase_signal in {"分化", "退潮"} or day_change <= -6:
|
||||
return "分化", "发酵阶段出现降温或赚钱效应弱化"
|
||||
return "发酵", "发酵状态延续"
|
||||
|
||||
if previous_phase == "高潮":
|
||||
if score < 25:
|
||||
return "冰点", "高潮后出现极端情绪坍塌"
|
||||
if climax_ready:
|
||||
return "高潮", "高潮条件继续成立"
|
||||
if score < 45 or systemic_health < 30:
|
||||
return "退潮", "高潮后风险快速释放"
|
||||
return "分化", "高潮条件消退，进入分化"
|
||||
|
||||
if previous_phase == "分化":
|
||||
if score < 25:
|
||||
return "冰点", "分化继续恶化至冰点区间"
|
||||
if score < 45 or systemic_health < 30:
|
||||
return "退潮", "分化后温度或系统健康度继续下降"
|
||||
if fermentation_confirmed:
|
||||
return "发酵", "分化转强条件连续两个交易日成立"
|
||||
return "分化", "分化延续，等待方向确认"
|
||||
|
||||
return phase_signal, "采用原始阶段信号"
|
||||
|
||||
|
||||
def build_sentiment_history(snapshots: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
payloads = _deduplicate_snapshots(snapshots)
|
||||
raw_rows = [_snapshot_stats(payload) for payload in payloads]
|
||||
results: list[dict[str, Any]] = []
|
||||
|
||||
for index, stats in enumerate(raw_rows):
|
||||
previous = raw_rows[:index]
|
||||
limit_history = [float(row["limit_up_count"]) for row in previous]
|
||||
down_limit_history = [float(row["limit_down_count"]) for row in previous]
|
||||
height_history = [float(row["max_height"]) for row in previous]
|
||||
three_plus_history = [float(row["three_plus_count"]) for row in previous]
|
||||
amount_history = [float(row["amount_billion"]) for row in previous[-20:] if row["amount_billion"]]
|
||||
|
||||
breadth_score = _clamp(float(stats["breadth_ratio"]))
|
||||
limit_strength = _adaptive_score(
|
||||
float(stats["limit_up_count"]),
|
||||
_linear(float(stats["limit_up_count"]), 10, 100),
|
||||
limit_history,
|
||||
)
|
||||
down_relief = 100 - _adaptive_score(
|
||||
float(stats["limit_down_count"]),
|
||||
_linear(float(stats["limit_down_count"]), 0, 50),
|
||||
down_limit_history,
|
||||
)
|
||||
seal_quality = _linear(float(stats["seal_rate"]), 35, 90)
|
||||
systemic_health = breadth_score * 0.60 + down_relief * 0.40
|
||||
systemic_gate = 1.0 if systemic_health >= 35 else 0.35 + systemic_health / 35 * 0.65
|
||||
ecology_base_score = limit_strength * 0.35 + seal_quality * 0.35 + down_relief * 0.30
|
||||
# Systemic risk is applied once to the final temperature. Reapplying it here
|
||||
# would count market breadth and limit-down pressure twice.
|
||||
limit_ecology_score = ecology_base_score
|
||||
|
||||
if stats["previous_limit_count"]:
|
||||
positive_score = float(stats["previous_positive_rate"])
|
||||
average_change_score = _clamp(50 + float(stats["average_previous_change"]) * 6)
|
||||
median_change_score = _clamp(50 + float(stats["median_previous_change"]) * 7)
|
||||
advance_score = _clamp(float(stats["advance_rate"]) * 2.5)
|
||||
severe_loss_safety = _clamp(100 - float(stats["severe_loss_rate"]) * 3)
|
||||
down_safety = _clamp(100 - float(stats["previous_down_count"]) / stats["previous_limit_count"] * 700)
|
||||
tail_safety_score = severe_loss_safety * 0.70 + down_safety * 0.30
|
||||
profit_effect_score = (
|
||||
positive_score * 0.30
|
||||
+ median_change_score * 0.25
|
||||
+ average_change_score * 0.10
|
||||
+ advance_score * 0.20
|
||||
+ tail_safety_score * 0.15
|
||||
)
|
||||
else:
|
||||
profit_effect_score = 50.0
|
||||
|
||||
max_height_score = _adaptive_score(
|
||||
float(stats["max_height"]),
|
||||
_linear(float(stats["max_height"]), 1, 7),
|
||||
height_history,
|
||||
)
|
||||
continuation_rate = (
|
||||
(float(stats["second_board_count"]) + float(stats["three_plus_count"]))
|
||||
/ max(float(stats["limit_up_count"]), 1)
|
||||
* 100
|
||||
)
|
||||
three_plus_density = float(stats["three_plus_count"]) / max(float(stats["limit_up_count"]), 1) * 100
|
||||
three_plus_score = _adaptive_score(
|
||||
float(stats["three_plus_count"]),
|
||||
_clamp(three_plus_density * 5),
|
||||
three_plus_history,
|
||||
)
|
||||
ladder_structure_score = (
|
||||
max_height_score * 0.30
|
||||
+ _clamp(continuation_rate * 3) * 0.25
|
||||
+ three_plus_score * 0.25
|
||||
+ float(stats["ladder_completeness"]) * 0.20
|
||||
)
|
||||
|
||||
amount_baseline = mean(amount_history) if amount_history else float(stats["amount_billion"] or 1)
|
||||
amount_ratio = float(stats["amount_billion"]) / max(amount_baseline, 1)
|
||||
amount_score = _clamp(50 + (amount_ratio - 1) * 100)
|
||||
limit_amount_share = float(stats["limit_amount_billion"]) / max(float(stats["amount_billion"]), 1) * 100
|
||||
liquidity_score = amount_score * 0.70 + _clamp(limit_amount_share * 20) * 0.30
|
||||
|
||||
component_scores = {
|
||||
"breadth": breadth_score,
|
||||
"limit_ecology": limit_ecology_score,
|
||||
"profit_effect": profit_effect_score,
|
||||
"ladder_structure": ladder_structure_score,
|
||||
"liquidity": liquidity_score,
|
||||
}
|
||||
raw_score = sum(component_scores[key] * weight / 100 for key, weight in COMPONENT_WEIGHTS.items())
|
||||
score = round(
|
||||
raw_score * systemic_gate
|
||||
)
|
||||
extreme_ice = float(stats["breadth_ratio"]) <= 15 and float(stats["limit_down_count"]) >= 100
|
||||
if extreme_ice:
|
||||
score = min(score, 15)
|
||||
elif float(stats["breadth_ratio"]) <= 25 and float(stats["limit_down_count"]) >= 50:
|
||||
score = min(score, 24)
|
||||
previous_scores: list[float] = []
|
||||
expected_date = str(stats.get("previous_trade_date") or "")
|
||||
for prior_result in reversed(results):
|
||||
if not expected_date or str(prior_result.get("trade_date") or "") != expected_date:
|
||||
break
|
||||
previous_scores.append(float(prior_result["score"]))
|
||||
expected_date = str(prior_result.get("previous_trade_date") or "")
|
||||
if len(previous_scores) == 3:
|
||||
break
|
||||
momentum = score - mean(previous_scores) if previous_scores else 0.0
|
||||
direction = "升温" if momentum > 3 else "降温" if momentum < -3 else "持平"
|
||||
normalization = "历史百分位" if len(previous) >= 20 else "固定锚点"
|
||||
previous_result = (
|
||||
results[-1]
|
||||
if results and str(stats.get("previous_trade_date") or "") == str(results[-1].get("trade_date") or "")
|
||||
else None
|
||||
)
|
||||
day_change = score - float(previous_result["score"]) if previous_result else 0.0
|
||||
ema_score = round(
|
||||
score if not previous_result
|
||||
else score * 0.5 + float(previous_result.get("ema_score", previous_result["score"])) * 0.5,
|
||||
1,
|
||||
)
|
||||
phase_signal = _phase_signal(score, momentum, profit_effect_score)
|
||||
fermentation_ready = (
|
||||
phase_signal == "发酵"
|
||||
and score >= 45
|
||||
and profit_effect_score >= 45
|
||||
and systemic_health >= 35
|
||||
and not extreme_ice
|
||||
)
|
||||
previous_fermentation_count = int(previous_result.get("fermentation_signal_count") or 0) if previous_result else 0
|
||||
fermentation_signal_count = previous_fermentation_count + 1 if fermentation_ready else 0
|
||||
phase, transition_reason = _confirmed_phase(
|
||||
previous_result,
|
||||
score,
|
||||
day_change,
|
||||
systemic_health,
|
||||
profit_effect_score,
|
||||
limit_ecology_score,
|
||||
phase_signal,
|
||||
extreme_ice,
|
||||
fermentation_signal_count,
|
||||
)
|
||||
previous_phase = str(previous_result.get("phase") or "") if previous_result else ""
|
||||
if phase not in {"修复", "分化"}:
|
||||
fermentation_signal_count = 0
|
||||
elif phase == "分化" and previous_phase != "分化":
|
||||
fermentation_signal_count = 0
|
||||
|
||||
components = {
|
||||
"breadth": {
|
||||
"label": "市场宽度",
|
||||
"score": round(breadth_score, 1),
|
||||
"weight": COMPONENT_WEIGHTS["breadth"],
|
||||
"summary": f"上涨占比 {stats['breadth_ratio']:.1f}%",
|
||||
},
|
||||
"limit_ecology": {
|
||||
"label": "涨停生态",
|
||||
"score": round(limit_ecology_score, 1),
|
||||
"weight": COMPONENT_WEIGHTS["limit_ecology"],
|
||||
"summary": (
|
||||
f"涨停 {stats['limit_up_count']} · 跌停 {stats['limit_down_count']} · "
|
||||
f"封板 {stats['seal_rate']:.1f}%"
|
||||
),
|
||||
},
|
||||
"profit_effect": {
|
||||
"label": "赚钱效应",
|
||||
"score": round(profit_effect_score, 1),
|
||||
"weight": COMPONENT_WEIGHTS["profit_effect"],
|
||||
"summary": (
|
||||
f"昨涨停红盘 {stats['previous_positive_rate']:.1f}% · "
|
||||
f"中位 {stats['median_previous_change']:+.2f}% · "
|
||||
f"重亏 {stats['severe_loss_rate']:.1f}%"
|
||||
if stats["previous_limit_count"] else "缺少前一交易日样本"
|
||||
),
|
||||
},
|
||||
"ladder_structure": {
|
||||
"label": "连板结构",
|
||||
"score": round(ladder_structure_score, 1),
|
||||
"weight": COMPONENT_WEIGHTS["ladder_structure"],
|
||||
"summary": f"最高 {stats['max_height']} 板 · 三板以上 {stats['three_plus_count']} 家",
|
||||
},
|
||||
"liquidity": {
|
||||
"label": "成交活跃度",
|
||||
"score": round(liquidity_score, 1),
|
||||
"weight": COMPONENT_WEIGHTS["liquidity"],
|
||||
"summary": f"成交 {stats['amount_billion']:.1f} 亿 · 均值比 {amount_ratio:.2f}",
|
||||
},
|
||||
}
|
||||
results.append(
|
||||
{
|
||||
**stats,
|
||||
"score": score,
|
||||
"ema_score": ema_score,
|
||||
"label": _sentiment_label(score),
|
||||
"phase": phase,
|
||||
"phase_signal": phase_signal,
|
||||
"transition_reason": transition_reason,
|
||||
"fermentation_signal_count": fermentation_signal_count,
|
||||
"day_change": round(day_change, 1),
|
||||
"direction": direction,
|
||||
"momentum": round(momentum, 1),
|
||||
"normalization": "250日历史百分位" if len(previous) >= 20 else normalization,
|
||||
"history_days": len(previous) + 1,
|
||||
"systemic_health": round(systemic_health, 1),
|
||||
"risk_multiplier": round(systemic_gate, 3),
|
||||
"components": components,
|
||||
}
|
||||
)
|
||||
return results
|
||||
|
||||
|
||||
def latest_contiguous_history(series: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
if not series:
|
||||
return []
|
||||
contiguous = [series[-1]]
|
||||
for row in reversed(series[:-1]):
|
||||
expected_previous = str(contiguous[0].get("previous_trade_date") or "")
|
||||
if not expected_previous or expected_previous != str(row.get("trade_date") or ""):
|
||||
break
|
||||
contiguous.insert(0, row)
|
||||
return contiguous
|
||||
|
||||
|
||||
def apply_sentiment_to_dashboard(
|
||||
dashboard: dict[str, Any],
|
||||
historical_snapshots: list[dict[str, Any]] | None = None,
|
||||
) -> dict[str, Any]:
|
||||
result = deepcopy(dashboard)
|
||||
history = list(historical_snapshots or [])
|
||||
history.append(result)
|
||||
series = build_sentiment_history(history)
|
||||
target_date = _trade_date(result)
|
||||
sentiment = next((row for row in reversed(series) if row["trade_date"] == target_date), None)
|
||||
if not sentiment:
|
||||
return result
|
||||
overview = dict(result.get("overview") or {})
|
||||
overview.update(
|
||||
{
|
||||
"sentiment_score": sentiment["score"],
|
||||
"sentiment_trend_score": sentiment["ema_score"],
|
||||
"sentiment_label": sentiment["label"],
|
||||
"sentiment_phase": sentiment["phase"],
|
||||
"sentiment_direction": sentiment["direction"],
|
||||
"sentiment_components": sentiment["components"],
|
||||
"sentiment_engine_version": SENTIMENT_ENGINE_VERSION,
|
||||
}
|
||||
)
|
||||
result["overview"] = overview
|
||||
return result
|
||||
sys.modules[__name__] = _implementation
|
||||
|
||||
Reference in New Issue
Block a user